Commit
•
4db66f4
1
Parent(s):
db766ef
Training in progress, epoch 1
Browse files- checkpoint-2138/config.json +36 -0
- checkpoint-2138/optimizer.pt +3 -0
- checkpoint-2138/pytorch_model.bin +3 -0
- checkpoint-2138/rng_state.pth +3 -0
- checkpoint-2138/scheduler.pt +3 -0
- checkpoint-2138/special_tokens_map.json +1 -0
- checkpoint-2138/tokenizer.json +0 -0
- checkpoint-2138/tokenizer_config.json +1 -0
- checkpoint-2138/trainer_state.json +31 -0
- checkpoint-2138/training_args.bin +3 -0
- config.json +36 -0
- pytorch_model.bin +3 -0
- runs/Oct09_18-55-42_patrick-general-gpu/1633805760.141876/events.out.tfevents.1633805760.patrick-general-gpu.63545.1 +3 -0
- runs/Oct09_18-55-42_patrick-general-gpu/events.out.tfevents.1633805760.patrick-general-gpu.63545.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
checkpoint-2138/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/fnet-large",
|
3 |
+
"actual_seq_length": 512,
|
4 |
+
"architectures": [
|
5 |
+
"FNetForSequenceClassification"
|
6 |
+
],
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"finetuning_task": "cola",
|
10 |
+
"hidden_act": "gelu_new",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "unacceptable",
|
15 |
+
"1": "acceptable"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 4096,
|
19 |
+
"label2id": {
|
20 |
+
"acceptable": 1,
|
21 |
+
"unacceptable": 0
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "fnet",
|
26 |
+
"num_hidden_layers": 24,
|
27 |
+
"pad_token_id": 3,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"tpu_short_seq_length": 512,
|
30 |
+
"transformers_version": "4.11.0.dev0",
|
31 |
+
"type_vocab_size": 4,
|
32 |
+
"use_fft": true,
|
33 |
+
"use_latest": false,
|
34 |
+
"use_tpu_fourier_optimizations": false,
|
35 |
+
"vocab_size": 32000
|
36 |
+
}
|
checkpoint-2138/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:debf193adf326eb84a2200e3263d5e166cab7e3759659f4392d01ac14d8035cc
|
3 |
+
size 1895696981
|
checkpoint-2138/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5367847041a08065ac86940bd3eed8e69753a47cfd0200c04c6930f72f8a6fad
|
3 |
+
size 947877033
|
checkpoint-2138/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39b4986d2a04fefcb5f3c993a446342c9b414527a968c5a9d22c32c9dc289b6c
|
3 |
+
size 14503
|
checkpoint-2138/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89b73cd68a76c22a44ad1cc8fefa0bc90e9bc321f8e764647ce08d49da6784ca
|
3 |
+
size 623
|
checkpoint-2138/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
checkpoint-2138/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2138/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}
|
checkpoint-2138/trainer_state.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 2138,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 1.3333333333333333e-05,
|
13 |
+
"loss": 0.6195,
|
14 |
+
"step": 2138
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 0.6526795029640198,
|
19 |
+
"eval_matthews_correlation": 0.0,
|
20 |
+
"eval_runtime": 22.7276,
|
21 |
+
"eval_samples_per_second": 45.891,
|
22 |
+
"eval_steps_per_second": 5.764,
|
23 |
+
"step": 2138
|
24 |
+
}
|
25 |
+
],
|
26 |
+
"max_steps": 6414,
|
27 |
+
"num_train_epochs": 3,
|
28 |
+
"total_flos": 5349643265353728.0,
|
29 |
+
"trial_name": null,
|
30 |
+
"trial_params": null
|
31 |
+
}
|
checkpoint-2138/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c02a7f6c24ee07ac2f2511cbd4d667a28e518dc0099c70b5bfe1bc64c969f04
|
3 |
+
size 2799
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/fnet-large",
|
3 |
+
"actual_seq_length": 512,
|
4 |
+
"architectures": [
|
5 |
+
"FNetForSequenceClassification"
|
6 |
+
],
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"finetuning_task": "cola",
|
10 |
+
"hidden_act": "gelu_new",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "unacceptable",
|
15 |
+
"1": "acceptable"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 4096,
|
19 |
+
"label2id": {
|
20 |
+
"acceptable": 1,
|
21 |
+
"unacceptable": 0
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "fnet",
|
26 |
+
"num_hidden_layers": 24,
|
27 |
+
"pad_token_id": 3,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"tpu_short_seq_length": 512,
|
30 |
+
"transformers_version": "4.11.0.dev0",
|
31 |
+
"type_vocab_size": 4,
|
32 |
+
"use_fft": true,
|
33 |
+
"use_latest": false,
|
34 |
+
"use_tpu_fourier_optimizations": false,
|
35 |
+
"vocab_size": 32000
|
36 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5367847041a08065ac86940bd3eed8e69753a47cfd0200c04c6930f72f8a6fad
|
3 |
+
size 947877033
|
runs/Oct09_18-55-42_patrick-general-gpu/1633805760.141876/events.out.tfevents.1633805760.patrick-general-gpu.63545.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:368806fd787a3b695fb878ec789d833f8931282e80a16579efce442e44493970
|
3 |
+
size 4369
|
runs/Oct09_18-55-42_patrick-general-gpu/events.out.tfevents.1633805760.patrick-general-gpu.63545.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d67d83bba39e084155b7345a862a151dd3c7881555afd12a19b8efeba8196a6
|
3 |
+
size 3761
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c02a7f6c24ee07ac2f2511cbd4d667a28e518dc0099c70b5bfe1bc64c969f04
|
3 |
+
size 2799
|